j-a-a-a-y
/

Huihui-Qwen3.5-27B-abliterated-W4A16-compressed-tensors

compressed-tensors

Model card Files Files and versions

Huihui-Qwen3.5-27B-abliterated-W4A16-compressed-tensors / recipe.yaml

j-a-a-a-y's picture

Upload W4A16 compressed-tensors quantization of Huihui-Qwen3.5-27B-abliterated

1bec8e2 verified 3 months ago

History Blame Contribute Delete

170 Bytes

	default_stage:
	default_modifiers:
	QuantizationModifier:
	targets: [Linear]
	ignore: [lm_head]
	scheme: W4A16
	bypass_divisibility_checks: false